Steer2Edit: From Activation Steering to Component-Level Editing
cs.CL
Submitted: 2026-02-10
Updated: 2026-11-08
Code: https://github.com/Trustworthy-MLLab/Steer2Edit
Terminology
Sources
- Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization
- Evaluating Large Language Models Trained on Code
- Editing Factual Knowledge in Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Fast Model Editing at Scale
- In-context Learning and Induction Heads
- Steering Language Models With Activation Engineering
- ReflCtrl: Controlling LLM Reflection Efficiently via Representation Engineering
- On the Role of Attention Heads in Large Language Model Safety
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data